Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction

Table 12

Summary of results for 2DCNN.

Architecture	Activation function	Mean
		RMSE	MAPE	IOA	R^2
CNN	Linear	19.6121	0.2407	0.8697	0.5928
	ReLU	22.1328	0.2706	0.8232	0.4814
	Sigmoid	26.0486	0.3214	0.6712	0.3927
	Softplus	22.7749	0.2649	0.7656	0.4798
Total		22.6421	0.2717	0.7842	0.4867